opencode-go upstream idle timeout on reasoning-heavy models with Effort=Max #30002

Activity

1. github-actions

   assigned

   fwang

   on May 30, 2026
2. github-actions commented on May 30, 2026

   

   github-actionsBot

   on May 30, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue doesn't fully meet our contributing guidelines.

   What needs to be fixed:

   • Missing required fields: OpenCode version, Operating System, Terminal, and Steps to reproduce are all left as _No response_. These are required for bug reports so maintainers can reproduce and diagnose the issue.
   • Please provide your OpenCode version, OS, and a minimal set of steps to reproduce the timeout.

   Please edit this issue to address the above within 2 hours, or it will be automatically closed.

   ---

   This issue might be a duplicate of an existing issue. Please check:

   • [BUG] "Upstream idle timeout exceeded" #28957: [BUG] "Upstream idle timeout exceeded" — reports the same upstream idle timeout error

   If you believe this was flagged incorrectly, please let a maintainer know.
3. github-actions

   added

   needs:complianceThis means the issue will auto-close after 2 hours.This means the issue will auto-close after 2 hours.

   on May 30, 2026
4. den317 commented on May 30, 2026

   

   den317

   on May 30, 2026

   Author

   More actions

   OS: macOS Tahoe 26.5
   CPU: Apple M4
   OpenCode Desktop: v1.15.12

   Steps to reproduce

   1. Open opencode in agent mode
   2. Select model: mimo-v2.5-pro (opencode-go provider)
   3. Set effort to Max
   4. Make sure you're in Build mode (not Plan)
   5. Submit a non-trivial coding task that involves generating 200+ lines of code (e.g., "implement a full essence tracker with evidence-based progress assessment across 7 alphas and 15 activity spaces")
   6. Wait ~3 minutes

   Expected behavior

   Model completes reasoning phase and starts streaming output tokens.

   Actual behavior

   After ~190-246 seconds an error appears: "Upstream idle timeout exceeded". No output tokens are received. Input tokens have already been billed.

   Working configurations

   • Build mode + Effort=Medium → ✅ works
   • Plan mode + Effort=Max → ✅ works
5. den317 commented on May 30, 2026

   

   den317

   on May 30, 2026

   Author

   More actions

   #28957 - it looks like it's the same issue here.
   Specific trigger:

   • Model: mimo-v2.5-pro
   • Mode: Build, Effort=Max
   • Plan + Effort=Max → ✅ works
   • Build + Effort=Medium → ✅ works

   The model spends 3–4 minutes in reasoning phase without emitting any tokens, then the upstream idle timeout (~190s) kills the connection. Input tokens are billed despite the failed output. A streaming reasoning_content field would fix this.
6. github-actions commented on May 30, 2026

   

   github-actionsBot

   on May 30, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

   Feel free to open a new issue that follows our issue templates.
7. github-actions

   removed

   needs:complianceThis means the issue will auto-close after 2 hours.This means the issue will auto-close after 2 hours.

   on May 30, 2026
8. github-actions

   closed this as not plannedon May 30, 2026